> I suppose that another option could be just to use classical > multi-dimensional scaling. By my understanding this is (if based on > Euclidian measure) completely analogous to PCA, and because it's based > explicitly on distances, I could easily exclude the variables with NA's on a > pairwise basis when calculating the distances.
I don't think it as straightforward as that because distances calculated on observations with missing values will be smaller than other distances. I suspect adjusting for this would be in some way equivalent to imputation. Exactly what do you want a low-dimensional representation of your data set for? (And why are you concerned about negative eigenvalues?) Hadley ______________________________________________ [email protected] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
